Articles (1): |
|
•
|
Deisenroth MP , Rasmussen CE and Peters J (March-2009) Gaussian Process Dynamic Programming
Neurocomputing 72(7-9) 1508-1524.
 
|
Conference papers (6): |
|
•
|
Wang Z , Deisenroth M , Ben Amor H , Vogt D , Schölkopf B and Peters J (July-2012) Probabilistic Modeling of Human Dynamics for Intention Inference
Robotics: Science and Systems (R:SS 2012), 1-8.
accepted

|
|
•
|
Rasmussen CE and Deisenroth MP (November-2008) Probabilistic Inference for Fast Learning in Control
In: EWRL 2008, 8th European Workshop on Reinforcement Learning, Springer, Berlin, Germany, 229-242.
 
|
|
•
|
Deisenroth MP , Peters J and Rasmussen CE (June-2008) Approximate Dynamic Programming with Gaussian Processes
In: ACC 2008, 2008 American Control Conference, IEEE Service Center, Piscataway, NJ, USA, 4480-4485.

|
|
•
|
Deisenroth MP , Rasmussen CE and Peters J (April-2008) Model-Based Reinforcement Learning with Continuous States and Actions
In: ESANN 2008, European Symposium on Artificial Neural Networks, d-side, Evere, Belgium, 19-24.

|
|
•
|
Deisenroth MP , Weissel F , Ohtsuka T and Hanebeck UD (July-2007) Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
In: ECC‘07, 9th European Control Conference, 3664-3671.

|
|
•
|
Deisenroth MP , Ohtsuka T , Weissel F , Brunn D and Hanebeck UD (September-2006) Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
In: MFI 2006, 6th IEEE International Conference on Multisensor Fusion and Integration, IEEE Service Center, Piscataway, NJ, USA, 371-376.
 
|
Theses (1): |
|
•
|
Deisenroth MP : An Online-Computation Approach to Optimal Finite-Horizon State-Feedback Control of Nonlinear Stochastic Systems, Universität Karlsruhe (TH), Karlsruhe, Germany, (August-30-2006).
Diplom thesis
|